https://repositorio.ifgoiano.edu.br/handle/prefix/217 Mon, 22 Jun 2026 15:06:20 GMT 2026-06-22T15:06:20Z https://repositorio.ifgoiano.edu.br/handle/prefix/6704 Título: BIOPROSPECÇÃO E POTENCIAL DE MITIGAÇÃO DO DÉFICIT HÍDRICO NA SOJA POR BACTÉRIAS PROMOTORAS DE CRESCIMENTO DE PLANTAS Autor(es): Tavares, Germanna Gouveia Primeiro Orientador: Costa, Alan Carlos Primeiro Membro da Banca: Silva, Adinan Alves da Segundo Membro da Banca: Müller, Caroline Terceiro Membro da Banca: Moura, Jadson Belém de Abstract: Soybean (Glycine max) is one of the most important agricultural commodities for global food supply; however, it frequently experiences yield losses due to environmental stresses, particularly drought. In addition, the crop has high nutritional requirements to achieve productivity levels that meet the growing global demand for food. This study investigated the potential of plant growth–promoting rhizobacteria (PGPR) to mitigate the drought effects in G. max and to enhance plant development. Initially, in vitro assays were carried out to identify functional traits of the bacteria, followed by genetic characterization. Based on this screening, 11 bacterial isolates, identified as belonging to the genus Bradyrhizobium spp., were selected according to the evaluated functional traits. Subsequently, two greenhouse experiments were carried out to simulate field conditions. The first experiment aimed to select bacteria with the greatest potential to promote the growth of inoculated plants, while the second evaluated the ability of these bacteria to enhance plant tolerance to water deficit. In both experiments, gas exchange, chlorophyll a fluorescence, photosynthetic pigments, and plant growth were assessed under well-watered and water-stress conditions, with and without inoculation using native or commercial bacteria, in addition to morphological evaluations of shoot and root systems. The results indicated that plant growth–promoting bacterial strains improved photosynthetic rates, electron transport efficiency, and root growth under both well-watered and drought stress conditions. Editor: Instituto Federal Goiano Tipo: Tese Fri, 20 Mar 2026 00:00:00 GMT https://repositorio.ifgoiano.edu.br/handle/prefix/6704 2026-03-20T00:00:00Z https://repositorio.ifgoiano.edu.br/handle/prefix/6513 Título: MICRO-ORGANISMOS PROMOTORES DO CRESCIMENTO VEGETAL PARA REDUÇÃO DA FERTILIZAÇÃO FOSFATADA EM SOJA E MILHO. Autor(es): Santos Junior, Jeronymo Pereira dos Primeiro Orientador: Souchie, Edson Luiz Primeiro Membro da Banca: Carlos, Leandro Segundo Membro da Banca: Ribeiro Neto, Moacir Abstract: With the expansion of agricultural frontiers and the migration of rural producers to the Cerrado, Brazil starts to break production records every agricultural year, mainly with soybean and corn crops. However, for this to happen, a great deal of research and technological development was necessary, especially in agricultural soil fertility management. The objective of this study was to evaluate the efficiency of different microbial consortia under different levels of phosphate fertilization in soybean and corn crops grown in the Cerrado. Two field trials (soybean and corn) were carried out in the 2023/24 summer harvest at the IF Goiano Experimental Area – Rio Verde Campus, GO. Both trials were randomized block designs, 3 x 5 factorial scheme (three levels of phosphate fertilization: 0, 50, and 100% of the recommended P dosage and five inoculation treatments: Azospirillum brasilense, Pseudomonas fluorescens, Azospirillum + Pseudomonas, Bacillus sp. + Paraburkholderia sp. and Priestia megaterium + Bacillus subtilis), with four replicates. Thirty-five days after emergence, in both trials, the following were evaluated: dry mass of the aerial part, roots, N and P contents in the aerial part and roots. For soybeans, the number and dry mass of nodules were also evaluated. At harvest, in both trials, the following were analyzed: mass of 1000 grains, N and P contents in the grains, and grain yield. The agronomic effectiveness of co-inoculation was proven to be a superior strategy, i.e., the combination of Priestia megaterium and Bacillus subtilis, or Bacillus and Paraburkholderia sp., or Azospirillum brasilense and Pseudomonas fluorescens is more favorable to soybean nutrition, growth, and productivity than isolated inoculation. Co-inoculation technologies (A. brasilense + P. fluorescens, Bacillus sp. + Paraburkholderia sp., and P. megaterium + B. subtilis) favor low-input systems as well as those aimed at optimizing the efficiency of conventional industrial phosphate fertilizers. The microbial isolates tested here as growth promoters acted synergistically and maximized the efficiency of phosphate fertilization in soybean crops. In corn cultivation, similarly, the co-inoculation of Priestia megaterium + Bacillus subtilis, or Bacillus sp. + Paraburkholderia sp., or even Azospirillum brasilense + Pseudomonas fluorescens enhanced corn productivity compared to the isolated inoculation of A. brasilense or P. fluorescens. Co-inoculation technologies (A. brasilense + P.fluorescens, Bacillus sp. + Paraburkholderia sp., and P. megaterium + B. subtilis) favored low-input systems as well as those aimed at optimizing the efficiency of conventional industrial phosphate fertilizers. Editor: Instituto Federal Goiano Tipo: Dissertação Fri, 05 Sep 2025 00:00:00 GMT https://repositorio.ifgoiano.edu.br/handle/prefix/6513 2025-09-05T00:00:00Z https://repositorio.ifgoiano.edu.br/handle/prefix/6436 Título: ANÁLISE RADIOGRÁFICA E MULTIESPECTRAL NA AVALIAÇÃO DA QUALIDADE DE SEMENTES DE Handroanthus impetiginosus Autor(es): Oliveira, Alessandra Mathias Primeiro Orientador: Sales, Juliana de Fátima Primeiro Membro da Banca: Teixeira, Marconi Batista Segundo Membro da Banca: Rodrigues, Arthur Almeida Terceiro Membro da Banca: Silva, Ingrid Maressa Hungria de Lima Abstract: Image analysis techniques are non-destructive, rapid, and objective alternatives to evaluate the quality of forest seeds. The lack of fast methods that do not compromise the seed for assessing the physiological quality of forest seeds hinders the efficiency of reforestation and conservation programs. Thus, the objective of this work was to evaluate the quality of purple ipe seeds (Handroanthus impetiginosus) using X-ray and multispectral image analysis techniques, integrated with physiological and morphometric parameters, to validate these complementary methodologies. Initially, with the seeds identified and numbered, radiographic images were obtained to classify the seeds into three classes according to the degree of filling of the embryonic cavity. Subsequently, with the same seeds, multispectral images were acquired in the near-infrared bands (880, 940, and 970 nm). With the seedlings from the emergence test, gas exchange analysis and chlorophyll A and B measurement were performed. Tests such as germination, seedling length, and electrical conductivity were also carried out. Subsequently, multivariate analysis of the data was performed using Principal Component Analysis (PCA). It was concluded that 80% of the evaluated seeds presented embryonic cavity filled by more than 50% (Class 1), corresponding to seeds that originated normal seedlings, while seeds with partial or absent filling were associated with abnormal seedlings and non-viable seeds, respectively. Viable seeds showed lower reflectance in NIR bands, a pattern associated with higher lipid content in tissues, and PCA efficiently integrated spectral, germinative, and photosynthetic variables, explaining 70.98% of the total variance in the first two components. Editor: Instituto Federal Goiano Tipo: Dissertação Wed, 11 Mar 2026 00:00:00 GMT https://repositorio.ifgoiano.edu.br/handle/prefix/6436 2026-03-11T00:00:00Z https://repositorio.ifgoiano.edu.br/handle/prefix/6137 Título: SISTEMAS INTELIGENTES EMBARCADOS EM DISPOSITIVOS MOVEIS E BASEADOS EM DEEP LEARNING PARA DETECÇÃO E MONITORAMENTO ESPACIAL DE PRAGAS AGRÍCOLAS Autor(es): Almeida, Guilherme Pires Silva de Primeiro Orientador: Santos, Leonardo Nazário Silva dos Primeiro Membro da Banca: Teixeira, Marconi Batista Segundo Membro da Banca: Oliveira, Mario Anderson de Terceiro Membro da Banca: Morais, Wilker Alves Abstract: Accurate and timely detection of insect pests remains one of the major challenges in modern agriculture, especially in large-scale soybean and maize production systems. Inefficient monitoring practices often result in delayed control interventions and significant yield losses. Recent advancements in deep learning and mobile computing have opened new opportunities for in-field pest identification using lightweight computer vision models. In this context, this thesis presents an integrated framework for intelligent pest detection and spatial monitoring based on deep learning, geostatistical analysis, and mobile applications. First, two datasets of insect pests were constructed and evaluated: a comprehensive high-resolution dataset curated through double-expert validation, and a smaller sample designed for comparative analysis. State-of-the-art detection architectures (YOLO and Detectron2) were trained on both datasets and subsequently converted into TensorFlow Lite (TFLite) and ONNX formats to enable deployment on resource-constrained devices. Even under the least favorable conditions using the reduced dataset and the lightest ONNX model the results reached a precision of 87.3% and accuracy 95.0%, demonstrating the robustness of the pipeline. Building upon these results, a mobile system named AgroInsect was developed. The application performs real-time, on-device detection of four key pest species relevant to Brazilian soybean and maize production (Diabrotica speciosa, Dalbulus maidis, Diceraeus spp., and Spodoptera frugiperda), automatically extracts geolocation metadata, validates spatial consistency based on field boundaries, and synchronizes detections with a cloud database. Spatial visualization is generated through heatmaps and Ordinary Kriging (PyKrige), enabling high-resolution incidence maps. Field evaluations confirmed strong model performance, with overall accuracy of 95.1%, F1-scores above 0.94 for all species, and only 1.1% false detections. The kriging model achieved R² > 0.94 under dense sampling, accurately reproducing ecological spatial patterns. Additionally, this thesis introduces AgroLabIA, a digital platform designed for the storage, annotation, and dissemination of agricultural pest datasets. It provides curated, multi-format datasets suitable for training machine learning models and supports the continuous expansion of new insect and weed classes. The integrated environment that encompasses dataset generation, mobile detection, spatial verification, and geostatistical mapping demonstrate a scalable and operationally robust solution for precision pest monitoring. The results position the AgroInsect database as an effective tool for accelerating decision-making in integrated pest management, particularly in regions with limited connectivity, thus contributing to the consolidation of Agriculture 4.0. Editor: Instituto Federal Goiano Tipo: Tese Sat, 29 Nov 2025 00:00:00 GMT https://repositorio.ifgoiano.edu.br/handle/prefix/6137 2025-11-29T00:00:00Z